Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mana-am/claude-f-meWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/mana-am/claude-f-me/play)<a href="https://agentmods.dev/commands/mana-am/claude-f-me/play"><img src="https://agentmods.dev/badge/commands/mana-am/claude-f-me/play/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/mana-am/claude-f-me/play"><img src="https://agentmods.dev/badge/commands/mana-am/claude-f-me/play.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00013 | $0.00177 |
| Opus 5 | $0.00006 | $0.00088 |
| Sonnet 5 | $0.00003 | $0.00035 |
| Haiku 4.5 | $0.00001 | $0.00018 |
Grade A, and why
play scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Using the claude-f-me MCP tools:
- If
list_devicesshows no devices, callscan_devicesfirst. - Start a building experience — call
start_gamewith typeescalation(gentle ramp that climbs and holds). If the user named a vibe ($ARGUMENTS), pick a fitting mode instead (e.g. "tease" →start_gametypeedge; "random" → a randomstart_game).
Reply in one short, playful line telling them what you started, and that they can say harder, softer, edge, surprise, or safeword at any time. Match the user's language (中文 if they wrote Chinese).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 15 lines · 13 tokens per session scan A f267fbb5e33f
play is a command published in the GitHub repository mana-am/claude-f-me (14 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 177 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
rvcsi-calibrate
Learn a v0 per-subcarrier baseline (mean amplitude) from a .rvcsi capture.
esp-harden
Harden and inspect ESP32 firmware for field failures, crashes, memory, and security.
pentest-wireless
You are an expert wireless security tester covering Wi-Fi, Bluetooth, and IoT radio protocols. For AUTHORIZED testing only.
put
Upload file to reMarkable (converts markdown to PDF).
device-info
A device-scanning command that identifies the connected chip and its VID:PID hardware identifiers. It also provides suggestions for the driver needed to use the device.